Research notes
Short reads on papers I'm building on — what the work does, and why it matters for systems where humans supervise and AI executes. These are notes on others' research, not my own publications.
Meta FAIR's tri-modal brain encoder won Algonauts 2025 by aligning pretrained model features to neural activity. Notes on why a predictive model of the brain matters for agent design.
Exploratory. No product thread yet.
Sakana AI's pipeline ideates, codes, runs experiments, and writes the paper — then reviews itself. Notes on what an autonomous research loop says about supervision.
In production: shaped iKount's rule that every deliverable ships with an attached review.
A self-referential framework where the agent monkey-patches its own logic toward a high-level goal. Notes on the design space it opens — and the supervision problem it sharpens.
In production: this is why KynDI assistants propose playbook changes for approval instead of self-modifying.